Evaluating Anomaly Detection Techniques in Industrial Environments: A Comparative Analysis of Autoencoders, Deep SVDD, and Supervised 2D CNNs
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0200445" target="_blank" >RIV/00216305:26220/26:0200445 - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/pages/publications/105025964847?origin=resultslist" target="_blank" >https://www.scopus.com/pages/publications/105025964847?origin=resultslist</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ACCESS.2025.3648909" target="_blank" >10.1109/ACCESS.2025.3648909</a>
Alternative languages
Result language
angličtina
Original language name
Evaluating Anomaly Detection Techniques in Industrial Environments: A Comparative Analysis of Autoencoders, Deep SVDD, and Supervised 2D CNNs
Original language description
As industrial systems become increasingly complex, the need to improve operational efficiency and ensure worker safety is more urgent than ever. Radar-based monitoring offers a promising solution, but the resulting high-dimensional data presents challenges for real-time analysis and anomaly detection. In this study, we propose a radar-based anomaly detection framework built on Orthogonal Time Frequency Space (OTFS) modulation, which transforms raw radar returns into informative spatio-temporal features. Our approach integrates three deep learning models—Deep SVDD, Autoencoders, and a supervised 2D Convolutional Neural Network (CNN)—to identify abnormal movements that deviate from typical worker behavior. To boost the performance of unsupervised methods, we introduce a dynamic thresholding mechanism that adjusts to shifts in environmental conditions, improving reliability in noisy and cluttered scenes. In evaluations using real-world radar data from industrial settings, the supervised 2D CNN achieved 99.9% accuracy, while all models recorded F1-scores between 0.98 and 0.99. Notably, Deep SVDD delivered the fastest inference time at 1.71 seconds, supporting the feasibility of real-time deployment. Additionally, lightweight Transformer-based models were compared, showing comparable accuracy but higher computational cost, reaffirming the practicality of the proposed designs for edge-oriented industrial sensing.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20202 - Communication engineering and systems
Result continuities
Project
<a href="/en/project/LUC24141" target="_blank" >LUC24141: Joint Communication and Sensing to Enhance Robustness of 6G Systems</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
IEEE Access
ISSN
2169-3536
e-ISSN
—
Volume of the periodical
13
Issue of the periodical within the volume
December 2025
Country of publishing house
US - UNITED STATES
Number of pages
11
Pages from-to
218044-218054
UT code for WoS article
001652569200012
EID of the result in the Scopus database
2-s2.0-105025964847